检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Salvatore Calcagno Raffaele Mineo Daniela Giordano Concetto Spampinato Department of Electrical Electronics and Computer Engineering Pattern Recognition and Computer Vision Laboratory (PeRCeiVe Lab) University of Catania Italy

In this short paper, we present the devised solutions for the subject identification and relapse detection tasks, which are part of the e-Prevention Challenge hosted at the ICASSP 2023 conference [1] [2] [3]. We specifically design an ensemble scheme of six models - five transformer-based ones and a CNN model - for the identification of subjects from wearable devices, while a personalized - one for each subject - scheme is used for relapse detection in psychotic disorder. Our final submitted solutions yield top performance on both tracks of the challenge: we ranked 2 nd on the subject identification task (with an accuracy of 93.85%) and 1 st on the relapse detection task (with a ROC-AUC and PR-AUC of about 0.65). Code and details are available at https://***/perceivelab/e-prevention-icassp-2023.

关键词： Performance evaluation Codes Wearable computers Signal processing Transformers Acoustics Object recognition

来源：评论

学校读者我要写书评

暂无评论

Finding discriminative filters for specific degradations in blind super-resolution 21

Finding discriminative filters for specific degradations in ...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Liangbin Xie Xintao Wang Chao Dong Zhongang Qi Ying Shan Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences and ARC Lab Tencent PCG ARC Lab Tencent PCG Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences and Shanghai AI Laboratory Shanghai China

ISBN: (纸本)9781713845393

Recent blind super-resolution (SR) methods typically consist of two branches, one for degradation prediction and the other for conditional restoration. However, our experiments show that a one-branch network can achieve comparable performance to the two-branch scheme. Then we wonder: how can one-branch networks automatically learn to distinguish degradations? To find the answer, we propose a new diagnostic tool – Filter Attribution method based on Integral Gradient (FAIG). Unlike previous integral gradient methods, our FAIG aims at finding the most discriminative filters instead of input pixels/features for degradation removal in blind SR networks. With the discovered filters, we further develop a simple yet effective method to predict the degradation of an input image. Based on FAIG, we show that, in one-branch blind SR networks, 1) we are able to find a very small number of (1%) discriminative filters for each specific degradation; 2) The weights, locations and connections of the discovered filters are all important to determine the specific network function. 3) The task of degradation prediction can be implicitly realized by these discriminative filters without explicit supervised learning. Our findings can not only help us better understand network behaviors inside one-branch blind SR networks, but also provide guidance on designing more efficient architectures and diagnosing networks for blind SR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trimap generation with background for natural image matting 3

Trimap generation with background for natural image matting

引用

3rd International Conference on Optics and Machine vision, ICOMV 2024

作者： Fu, Qian Liang, Yihui Kun, Zou Feng, Fujian Xu, Xiang School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China

ISBN: (纸本)9781510680319

Image matting is a widely-used image processing technique that aims at accurately separating foreground from an image. However, this is a challenging and ill-posed problem that demands additional input, such as trimaps and background images, for providing prior knowledge. However, the manual annotation of trimaps require lots of labor, limiting the application of trimap-based methods. Some trimap-free methods explore alternatives with low labor requirements by utilizing captured background images, including background-based methods. However, the quality of alpha mattes predicted by trimap-free methods still fall short of trimap-based methods. To reduce the performance gap between background-based and trimap-based methodes, we present Trimap Generation from Background Image (TG-BG) method which can generate trimaps from the input image and a captured background image. It provides an economical solution to facilitate the application of trimap-based methods, allowing for low-cost and high-quality alpha matte predictions. TP-BG leverages a ViT backbone for feature extraction and employs the Image and Background Detail Fusion Stream (IBDFS) to capture multi-scale detail information. The introduction of foreground impact loss encourages the network to pay more attention to the foreground in the image. We validate the trimap prediction performance of TP-BG by comparing the alpha matte quality obtained by background-based methods and that obtained by trimap-based methods integrated with TP-BG. The experimental results demonstrate that TP-BG can generate high-quality trimap from a background image, and trimap-based methods integrated with TP-BG outperform the state-of-the-art background-based methods in terms of four alpha matte quality metrics. © 2024 SPIE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Deform-CAM: Self-attention Based on Deformable Convolution for Weakly Supervised Semantic Segmentation 17th

Deform-CAM: Self-attention Based on Deformable Convolution f...

引用

17th Chinese Conference on Image and Graphics Technologies and Applications, IGTA 2022

作者： Huang, Feihong Wang, Da-Han Ye, Hai-Li Zhu, Shunzhi School of Computer and Information Engineering Xiamen University of Technology Xiamen China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen China

ISBN: (纸本)9789811950957

Weakly-supervised semantic segmentation (WSSS) receives increasing attentions from the community in recent years as it leverages the weakly annotated data to solve the problem of lacking of fully annotated data. Among them, the WSSS method based on image-level annotation is the most direct and effective while the image-level annotation is easy to obtain. Most advanced methods use class activation maps (CAM) as initial pseudo-labels, however, they only identify local regions of the target, while ignoring the context information among local regions. To solve this problem, this paper proposes a deformable convolution based self-attention module (DSAM), which introduces a pixel relationship matrix, to learn the contextual information of the image. A regularization loss is introduced to narrow the distance between the DSAM and the CAM. Compared to the base CAM method, our method can identify more target features and robustly improve the performance of WSSS without training the classifier multiple times. Our proposed method achieves the mIoU of 65.5% and 66.8% on the Pascal VOC 2012 val and test sets, respectively, demonstrating the feasibility of the method. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Video matting based on local-global features fusion 4

Video matting based on local-global features fusion

引用

4th International Conference on Machine Learning and computer Application, ICMLCA 2023

作者： Dong, Niuniu Liang, Yihui Zou, Kun Li, Wensheng Feng, Fujian School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China

ISBN: (数字)9781510680265

ISBN: (纸本)9781510680258

Video matting aims at accurately separating foreground from videos. Recent video matting researches pursue to eliminate auxiliary inputs. However, due to the limited ability of extracting global correlation features, these methods suffer from performance degradation when dealing with complex scenes or natural background videos. To address this challenge, we propose a video matting method called Video Matting Based on Local-Global Features Fusion (VMBLGFF) which can extract both comprehensive global correlation features and local subtle features. VMBLGFF contains two closely connected networks: a transformer network that utilizes window and global attention mechanisms to obtain global correlation features within and cross windows, and a fusion network that integrates local subtle features into the global correlation features to supplement the local detail information which may be overlooked by the attention mechanisms. VMBLGFF alleviates the issue of limiting global correlation features and has been benchmarked on both synthetic and real datasets, and the results demonstrate that VMBLGFF improves the quality of video matting and exhibits good generalization performance. © 2024 SPIE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Neural Transformation Fields for Arbitrary-Styled Font Generation

Neural Transformation Fields for Arbitrary-Styled Font Gener...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Bin Fu Junjun He Jianjun Wang Yu Qiao ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shanghai Artificial Intelligence Laboratory

Few-shot font generation (FFG), aiming at generating font images with a few samples, is an emerging topic in recent years due to the academic and commercial values. Typically, the FFG approaches follow the style-content disentanglement paradigm, which transfers the target font styles to characters by combining the content representations of source characters and the style codes of reference samples. Most existing methods attempt to increase font generation ability via exploring powerful style representations, which may be a sub-optimal solution for the FFG task due to the lack of modeling spatial transformation in transferring font styles. In this paper, we model font generation as a continuous transformation process from the source character image to the target font image via the creation and dissipation of font pixels, and embed the corresponding transformations into a neural transformation field. With the estimated transformation path, the neural transformation field generates a set of intermediate transformation results via the sampling process, and a font rendering formula is developed to accumulate them into the target font image. Extensive experiments show that our method achieves state-of-the-art performance on few-shot font generation task, which demonstrates the effectiveness of our proposed model. Our implementation is available at: https://***/fubinfb/NTF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TOWARDS CODABLE WATERMARKING FOR INJECTING MULTI-BITS INFORMATION TO LLMS 12

TOWARDS CODABLE WATERMARKING FOR INJECTING MULTI-BITS INFORM...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Wang, Lean Yang, Wenkai Chen, Deli Zhou, Hao Lin, Yankai Meng, Fandong Zhou, Jie Sun, Xu National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Gaoling School of Artificial Intelligence Renmin University of China China Pattern Recognition Center WeChat AI Tencent Inc. China DeepSeek AI China

As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing whether a text is generated by LLMs by injecting hidden patterns. However, we argue that existing LLM watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs (such as encoding model version, generation time, user id, etc.). In this work, we conduct the first systematic study on the topic of Codable Text Watermarking for LLMs (CTWL) that allows text watermarks to carry multi-bit customizable information. First of all, we study the taxonomy of LLM watermarking technologies and give a mathematical formulation for CTWL. Additionally, we provide a comprehensive evaluation system for CTWL: (1) watermarking success rate, (2) robustness against various corruptions, (3) coding rate of payload information, (4) encoding and decoding efficiency, (5) impacts on the quality of the generated text. To meet the requirements of these non-Pareto-improving metrics, we follow the most prominent vocabulary partition-based watermarking direction, and devise an advanced CTWL method named Balance-Marking. The core idea of our method is to use a proxy language model to split the vocabulary into probability-balanced parts, thereby effectively maintaining the quality of the watermarked text. Extensive experimental results show that our method outperforms the baseline under comprehensive evaluation. Our code is available at https://***/lancopku/codable-watermarking-for-llm. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Dlung:Unsupervised Few-Shot Diffeomorphic Respiratory Motion Modeling

引用

Journal of Shanghai Jiaotong university(Science) 2023年第4期28卷 536-545页

作者：陈培芝郭逸凡王大寒陈金铃 College of Computer and Information Engineering Xiamen University of TechnologyXiamen 361024FujianChina Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen 361024FujianChina School of Information Engineering Changchun Sci-Tech UniversityChangchun 130600China Department of Computer Science and Information Engineering Chaoyang University of TechnologyTaichung 41349TaiwanChina

Lung image registration plays an important role in lung analysis applications,such as respiratory motion *** learning-based image registration methods that can compute the deformation without the requirement of supervision attract much ***,it is noteworthy that they have two drawbacks:they do not handle the problem of limited data and do not guarantee diffeomorphic(topologypreserving)properties,especially when large deformation exists in lung *** this paper,we present an unsupervised few-shot learning-based diffeomorphic lung image registration,namely *** employ fine-tuning techniques to solve the problem of limited data and apply the scaling and squaring method to accomplish the diffeomorphic ***,atlas-based registration on spatio-temporal(4D)images is performed and thoroughly compared with baseline *** achieves the highest accuracy with diffeomorphic *** constructs accurate and fast respiratory motion models with limited *** research extends our knowledge of respiratory motion modeling.

关键词： unsupervised few-shot learning respiratory motion modeling diffeomorphic registration

来源：评论

学校读者我要写书评

暂无评论

Exploring Joint Information of Multi-Scales for Vehicle Re-Identification 22

Exploring Joint Information of Multi-Scales for Vehicle Re-I...

引用

8th International Conference on Computing and Artificial Intelligence, ICCAI 2022

作者： Zhou, Yongjie Wang, Dahan School of Computer and Information Engineering Xiamen University of Technology Xiamen Chinese Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China

ISBN: (纸本)9781450396110

Vehicle re-identification (re-ID) is an essential component of intelligent video surveillance, which attempts to solve the problem of retrieving specific vehicle instances. The technical challenge is mainly the requirement that the algorithm be robust under different viewing angles, resolutions, occlusions, and lighting conditions, yet different conditions can arise where the appearance of the exact vehicle varies dramatically. In contrast, the appearance of two different vehicles is exceptionally similar. To overcome this enormous challenge: we adopt a novel multi-scales attention network architecture, which will feature representation for feature maps at different scales to enhance the recognition of intricate parts, and introduce an inter-coordinate attention module to build interdependencies between component positions, making it possible to build a more robust vehicle model feature representation, and finally this paper also proposes a camera-based vehicle re localization method that enables the model to calculate the vehicle occurrence probability using the potential information among road network cameras as a post-processing step to re-correct the confidence level of the re-identification ranking. Experimental results show that the method outperforms the reference method in all indexes even without post-processing. At the same time, the camera confidence correction can be used in overlay with the reordering clustering correction method, which can improve the results by four percentage points and MAP up to 81.4%. © 2022 ACM.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Sustainable Mining in the Era of Artificial Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 1-4页

作者： Long Chen Yuting Xie Yutong Wang Shirong Ge Fei-Yue Wang IEEE the State Key Laboratory for Management and Control of Complex Systems at the Institute of Automation Chinese Academy of SciencesBeijing 100190China the National Laboratory of Pattern Recognition at the Institute of Automation and Waytous Ltd.China the School of Computer Science and Engineering Sun Yat-Sen UniversityGuangzhou 510275GuangdongChina the School of Mechanical Electronic and Information Engineering China University of Mining and Technology BeijingBejing 100083China the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190China

The mining sector historically drove the global economy but at the expense of severe environmental and health repercussions,posing sustainability challenges[1]-[3].Recent advancements on artificial intelligence(AI)are revolutionizing mining through robotic and data-driven innovations[4]-[7].While AI offers mining industry advantages,it is crucial to acknowledge the potential risks associated with its widespread ***-reliance on AI may lead to a loss of human control over mining operations in the future,resulting in unpredictable consequences.

关键词： Sustainable mining consequences

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：